Dr. Kedar Hippalgaonkar, Institute of Materials Research and Engineering at the Agency for Science Technology and Research (A*STAR) and Materials Science and Engineering Department at Nanyang Technological University (NTU)
Accelerating Materials Development through High Throughput Experiments, Machine Learning and High Performance Computing
Abstract: The design of functional materials, both purely inorganic compounds as well as inorganic-organic hybrids is a difficult challenge due to the large state space in the Structure-Process-Property-Performance paradigm. The process of Materials-by-Design constitutes multiple steps including (A) invertible representations of structure, followed by (B) creation of a database of out-of-equilibrium functional properties, and finally (C) Machine Learning models. Synthesis of new materials and composites requires process parameter tuning, where Bayesian Optimization is powerful. I will describe our platform technology development using high-throughput robotic experimentation with automated bayesian optimization to design new materials. We inverse design their performance via machine learning models. Further, the ability to generate new, previously unseen materials with desired properties is possible through the development of generative machine learning models; I will describe our efforts towards such materials discovery.
Bio: Dr. Kedar Hippalgaonkar is a Senior Scientist at the Institute of Materials Research and Engineering at the Agency for Science Technology and Research (A*STAR) and an Assistant Professor at the Materials Science and Engineering Department at Nanyang Technological University (NTU). He leads a multi-PI program on Accelerating Materials Development for Manufacturing. The program focuses on the development of new materials, processes and optimization using Machine Learning, AI robotics and high-throughput computations and experiments in functional and structural materials.